The accurate prediction of bearing capacity is crucial in ensuring the structural integrity and safety of pile foundations. This research compares the Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) algorithms utilizing a data set of 257 dynamic pile load tests for the first time. Also, this research illustrates the multicollinearity effect on DNN, CNN, RNN, LSTM, and BiLSTM models’ performance and accuracy for the first time. A comprehensive comparative analysis is conducted, employing various statistical performance parameters, rank analysis, and error matrix to evaluate the performance of these models. The performance is further validated using external validation, and visual interpretation is provided using the regression error characteristics (REC) curve and Taylor diagram. Results from the comparative analysis reveal that the DNN (Coefficient of determination (R²)_{training (TR)} = 0.97, root mean squared error (RMSE)_TR = 0.0413; R²_{testing (TS)} = 0.9, RMSE_TS = 0.08) followed by BiLSTM (R²_TR = 0.91, RMSE_TR = 0.782; R²_TS = 0.89, RMSE_TS = 0.0862) model demonstrates the highest performance accuracy. It is noted that the BiLSTM model is better than LSTM because the BiLSTM model, which increases the amount of information for the network, is a sequence processing model made up of two LSTMs, one of which takes the input in a forward manner, and the other in a backward direction. The prediction of pile-bearing capacity is strongly influenced by ram weight (having a considerable multicollinearity level), and the effect of the considerable multicollinearity level has been determined for the model based on the recurrent neural network approach. In this study, the recurrent neural network model has the least performance and accuracy in predicting the pile-bearing capacity.

Shield tunnel lining is prone to water leakage, which may further bring about corrosion and structural damage to the walls, potentially leading to dangerous accidents. To avoid tedious and inefficient manual inspection, many projects use artificial intelligence (AI) to detect cracks and water leakage. A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper. Our proposal includes a ConvNeXt-S backbone, deconvolutional-feature pyramid network (D-FPN), spatial attention module (SPAM). and a detection head. It can extract representative features of leaking areas to aid inspection processes. To further improve the model’s robustness, we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples. Validation experiments are performed, achieving the average precision (AP) score of 56.8%, which outperforms previous work by a margin of 5.7%. Visualization illustrations also support our method’s practical effectiveness.

Digital fabrication techniques, in recent decades, have provided the basis of a sustainable revolution in the construction industry. However, selecting the digital fabrication method in terms of manufacturability and functionality requirements is a complex problem. This paper presents alternatives and criteria for selection of digital fabrication techniques by adopting the multi-criteria decision-making technique. The alternatives considered in the study are concrete three-dimensional (3D) printing, shotcrete, smart dynamic casting, material intrusion, mesh molding, injection concrete 3D printing, and thin forming techniques. The criteria include formwork utilization, reinforcement incorporation, geometrical complexity, material enhancement, assembly complexity, surface finish, and build area. It demonstrates different multi-criteria decision-making techniques, with both subjective and objective weighting methods. The given ranking is based on the current condition of digital fabrication in the construction industry. The study reveals that in the selection of digital fabrication techniques, the criteria including reinforcement incorporation, build area, and geometrical complexity play a pivotal role, collectively accounting for nearly 70% of the overall weighting. Among the evaluated techniques, concrete 3D printing emerged as the best performer, however the shotcrete and mesh molding techniques in the second and third positions.

This paper delves into the lateral load-bearing behavior of lattice-shaped diaphragm wall (LSDW), a novel type of diaphragm wall foundation with many engineering advantages. By employing a double-layer wall structure for the first time in laboratory settings, the research presents an innovative testing methodology, complete with novel computational formulas, to accurately measure the responses of LSDW’s inner and outer walls under varying loads. It is found that the Q–s curves of LSDWs exhibit a continuous, progressive deformation and failure characteristic without any abrupt drops, and the standard for judging the horizontal bearing capacity of LSDW foundations should be based on the allowable displacement of the superstructure. The bearing capacity for the double-chamber LSDWs was found to be approximately 1.68 times that of the single-chamber structure, pointing to a complex interplay between chamber number and structural capacity that extends beyond a linear relationship and incorporates the group wall effect. The study also reveals that LSDWs act as rigid bodies with minimal angular displacement and a consistent tilting deformation, peaking in bending moment at about 0.87 of wall depth from the mud surface, across different chamber configurations. Furthermore, it can be found that using the p–y curve method for analyzing the horizontal behavior of LSDW foundations is feasible, and the hyperbolic p–y curve method offers higher accuracy in calculations. These insights offer valuable guidance for both field and laboratory testing of LSDWs and aid in the design and calculation of foundations under horizontal loads.

To completely solve the problem of fatigue cracking issue of orthotropic steel bridge decks (OSDs), the authors proposed a steel–ultra-high performance concrete (UHPC) lightweight composite deck (LWCD) with closed ribs in 2010. Based on the successful application of that LWCD, an adaptation incorporating an innovative composite deck structure, i.e., the hot-rolled section steel–UHPC composite deck with open ribs (SSD) is proposed in this paper, aiming to simplify the fabrication process as well as to reduce the cost of LWCD. Based on a long-span cable-stayed bridge, a design scheme is proposed and is compared with the conventional OSD scheme. Further, a finite element (FE) calculation is conducted to reflect both the global and local behavior of the SSD scheme, and it is found that the peaked stresses in the SSD components are less than the corresponding allowable values. A static test is performed for an SSD strip specimen to understand the anti-cracking behavior of the UHPC layer under negative bending moments. The static test results indicate that the UHPC layer exhibited a satisfactory tensile toughness, the UHPC tensile strength obtained from the test is 1.8 times the calculated stress by the FE model of the real bridge. In addition, the fatigue stresses of typical fatigue-prone details in the SSD are calculated and evaluated, and the influences of key design parameters on the fatigue performance of the SSD are analyzed. According to the fatigue results, the peaked stress ranges for all of the 10 fatigue-prone details are within the corresponding constant amplitude fatigue limits. Then a fatigue test is carried out for another SSD strip specimen to explore the fatigue behavior of the fillet weld between the longitudinal and transverse ribs. The specimen failed at the fillet weld after equivalent 47.5 million cycles of loading under the design fatigue stress range, indicating that the fatigue performance of the SSD could meet the fatigue design requirement. Theoretical calculations and experiments provide a basis for the promotion and application of this structure in bridge engineering.

The derivation and validation of analytical equations for predicting the tensile initial stiffness of thread-fixed one-side bolts (TOBs), connected to enclosed rectangular hollow section (RHS) columns, is presented in this paper. Two unknown stiffness components are considered: the TOBs connection and the enclosed RHS face. First, the trapezoidal thread of TOB, as an equivalent cantilevered beam subjected to uniformly distributed loads, is analyzed to determine the associated deformations. Based on the findings, the thread-shank serial-parallel stiffness model of TOB connection is proposed. For analysis of the tensile stiffness of the enclosed RHS face due to two bolt forces, the four sidewalls are treated as rotation constraints, thus reducing the problem to a two-dimensional plate analysis. According to the load superposition method, the deflection of the face plate is resolved into three components under various boundary and load conditions. Referring to the plate deflection theory of Timoshenko, the analytical solutions for the three deflections are derived in terms of the variables of bolt spacing, RHS thickness, height to width ratio, etc. Finally, the validity of the above stiffness equations is verified by a series of finite element (FE) models of T-stub substructures. The proposed component stiffness equations are an effective supplement to the component-based method.

As urban construction continues to develop and automobile ownership rises, parking shortages in cities have become increasingly acute. Given the limited availability of land resources, conventional underground garages and parking buildings no longer suffice to meet the growing demand for parking spaces. To address this dilemma, underground parking shaft (UPS) has emerged as a highly regarded solution. This study provides an overview of the layout scheme, structural design approaches, and construction techniques for UPS, focusing on the characteristics of intensive construction demonstrated in the project located in the Jianye District of Nanjing. Compared to conventional vertical shaft garage construction methods, this assembly parking shaft offers advantages such as a smaller footprint, higher prefabrication rate, shorter construction period, and reduced environmental impact. It presents an efficient approach for the intensive construction of urban underground spaces, particularly in areas with limited land and complex environments, showing promising prospects for widespread application.

This paper proposes an accurate, efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network (CNN). The state-of-the-art robust CNN model (EfficientNet) is applied to tunnel wall image recognition. Gaussian filtering, data augmentation and other data pre-processing techniques are used to improve the data quality and quantity. Combined with transfer learning, the generality, accuracy and efficiency of the deep learning (DL) model are further improved, and finally we achieve 89.96% accuracy. Compared with other state-of-the-art CNN architectures, such as ResNet and Inception-ResNet-V2 (IRV2), the presented deep transfer learning model is more stable, accurate and efficient. To reveal the rock classification mechanism of the proposed model, Gradient-weight Class Activation Map (Grad-CAM) visualizations are integrated into the model to enable its explainability and accountability. The developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou, China, with great results.

Raveling is a common distress of asphalt pavements, defined as the removal of stones from the pavement surface. To predict and assess raveling quantitatively, a cumulative damage model based on an energy dissipation approach has been developed at the meso level. To construct the model, a new test method, the pendulum impact test, was employed to determine the fracture energy of the stone-mastic-stone meso-unit, while digital image analysis and dynamic shear rheometer test were used to acquire the strain rate of specimens and the rheology property of mastic, respectively. Analysis of the model reveals that when the material properties remain constant, the cumulative damage is directly correlated with loading time, loading amplitude, and loading frequency. Specifically, damage increases with superimposed linear and cosine variations over time. A higher stress amplitude results in a more rapidly increasing rate of damage, while a lower load frequency leads to more severe damage within the same loading time. Moreover, an example of the application of the model has been presented, showing that the model can be utilized to estimate failure life due to raveling. The model is able to offer a theoretical foundation for the design and maintenance of anti-raveling asphalt pavements.

The thixotropic structural build-up is crucial in extrusion-based three-dimensional (3D) concrete printing. This paper uses a theoretical model to predict the evolution of static and dynamic yield stress for printed concrete. The model employs a structural kinetics framework to create a time-independent constitutive link between shear stress and shear rate. The model considers flocculation, deflocculation, and chemical hydration to anticipate structural buildability. The reversible and irreversible contributions that occur throughout the build-up, breakdown, and hydration are defined based on the proposed structural parameters. Additionally, detailed parametric studies are conducted to evaluate the impact of model parameters. It is revealed that the proposed model is in good agreement with the experimental results, and it effectively characterizes the structural build-up of 3D printable concrete.

The importance of geometrical control of three dimensional (3D) printable concrete without the support of formwork is widely acknowledged. In this study, a numerical model based on computational fluid dynamics was developed to evaluate the geometrical quality of a 3D printed layer. The numerical results were compared, using image analysis, with physical cross-sectional sawn samples. The influence of printing parameters (printing speed, nozzle height, and nozzle diameter) and the rheological behavior of printed materials (yield stress), on the geometrical quality of one printed layer was investigated. In addition, the yield zone of the printed layer was analyzed, giving insights on the critical factors for geometrical control in 3D concrete printing. Results indicated that the developed model can precisely describe the extrusion process, as well as the cross-sectional quality.

In this study, we propose the use of a fiber-reinforced plastic grid with polymer−cement−mortar (FRP Grid-PCM) to reinforce segment joints in tunnel shield linings. These joints play a crucial role in determining bearing capacity but are vulnerable to deterioration during operation. To investigate how to enhance the flexural performance of longitudinal shield lining joints, we built eccentric short column specimens by bolting two half-corbel columns together and tested them in the laboratory. The test program comprised two control specimens and three strengthened specimens with FRP grid applied on one side, away from the axial load. The tests varied two main parameters: loading eccentricity and the number of FRP grid layers. We conducted a detailed analysis of the failure process, bearing capacity, and bending stiffness of longitudinal joints under different conditions. Furthermore, we developed an analytical model to predict the flexural bearing capacity of longitudinal joints upgraded with the FRP Grid-PCM method and validated it through experimental results. The research demonstrates that the FRP grid effectively reduces joint opening and rotation angles while enhancing the bearing capacity of the short column, particularly with concurrent increases in loading eccentricity and the number of FRP grid layers. Overall, our findings offer a novel alternative for improving the flexural performance of longitudinal joints in shield tunnels.

Reasonable prediction of concrete creep is the basis of studying long-term deflection of concrete structures. In this paper, a hybrid model-driven and data-driven (HMD) method for predicting concrete creep is proposed by using the sequence integration strategy. Then, a novel uncertainty prediction model (UPM) is developed considering uncertainty quantification. Finally, the effectiveness of the proposed method is validated by using the North-western University (NU) database of creep, and the effect of uncertainty on prediction results are also discussed. The analysis results show that the proposed HMD method outperforms the model-driven and three data-driven methods, including the genetic algorithm-back propagation neural network (GA-BPNN), particle swarm optimization-support vector regression (PSO-SVR) and convolutional neural network only method, in accuracy and time efficiency. The proposed UPM of concrete creep not only ensures relatively good prediction accuracy, but also quantifies the model and measurement uncertainties during the prediction process. Additionally, although incorporating measurement uncertainty into concrete creep prediction can improve the prediction performance of UPM, the prediction interval of the creep compliance is more sensitive to model uncertainty than to measurement uncertainty, and the mean contribution of variance attributed to the model uncertainty to the total variance is about 90%.

The mechanical and durability characteristics of concrete are crucial for designing and evaluating concrete structures throughout their entire operational lifespan. The main objective of this research is to use the deep learning (DL) method along with an artificial neural network (ANN) to predict the chloride migration coefficient and concrete compressive strength. An expansive experimental database of nearly 1100 data points was gathered from existing scientific literature. Four forecast models were created, utilizing between 10 and 12 input features. The ANN was used to address the missing data gaps in the literature. A comprehensive pre-processing approach was then implemented to identify outliers and encode data attributes. The use of mean absolute error (MAE) as an evaluation metric for regression tasks and the employment of a confusion matrix for classification tasks were found to produce accurate results. Additionally, both the compressive strength and chloride migration coefficient exhibit a high level of accuracy, above 0.85, in both regression and classification tasks. Moreover, a user-friendly web application was successfully developed in the present study using the Python programming language, improving the ability to integrate smoothly with the user’s device.

The recycled powder (RP) from construction wastes can be used to partially replace cement in the preparation of reactive powder concrete. In this paper, reactive powder concrete mixtures with RP partially replacing cement, and natural sand instead of quartz, are developed. Standard curing is used, instead of steam curing that is normally requested by standard for reactive powder concrete. The influences of RP replacement ratio (0, 10%, 20%, 30%), silica fume proportion (10%, 15%, 20%), and steel fiber proportion (0, 1%, 2%) are investigated. The effects of RP, silica fume, and steel fiber proportion on compressive strength, elastic modulus, and relative absorption energy are analyzed, and theoretical models for compressive strength, elastic modulus, and relative absorption energy are established. A constitutive model for the uniaxial compressive stress–strain relationship of reactive powder concrete with RP is developed. With the increase of RP replacement ratio from 0% to 30%, the compressive strength decreases by 42% and elastic modulus decreases by 24%.

Concrete is the most widely utilized material for construction purposes, second only to water, in the ever-increasing need for construction globally. Concrete is a brittle material and possesses a high risk of crack formation and consequent deterioration. Cracking, which allows chemicals to enter and can cause concrete structures to lose their physico-mechanical and durability features. Repairing and rehabilitating concrete structures involves high costs and leads to various repair methods including coating, adhesives, polymers, supplementary cementitious materials (SCMs), and fibers. One of the latest technologies is the use of microorganisms in concrete. These added microorganisms lead to calcite precipitation and thereby heal the cracks effectively. This study presents a comprehensive literature survey on bacteria-included concrete, before which a bibliographic survey is performed using VOSViewer software. In addition to regular bacterial concrete, this study focuses on also using SCMs and fibers in bacterial concrete. A detailed literature review with data representation for various mechanical properties including compressive strength (CS), split tensile strength (SS), and flexure strength (FS), along with durability properties including carbonation, water absorption, resistance against chloride ion penetration, gas permeation, and resistance against cyclic freeze-and-thaw is presented. A study on the use of X-ray computed tomography (XCT) in bacterial concrete is highlighted, and the scope for future research, along with identification of the research gap, is presented.

Quality assurance and maintenance play a crucial role in engineering construction, as they have a significant impact on project safety. One common issue in concrete structures is the presence of defects. To enhance the automation level of concrete defect repairs, this study proposes a computer vision-based robotic system, which is based on three-dimensional (3D) printing technology to repair defects. This system integrates multiple sensors such as light detection and ranging (LiDAR) and camera. LiDAR is utilized to model concrete pipelines and obtain geometric parameters regarding their appearance. Additionally, a convolutional neural network (CNN) is employed with a depth camera to locate defects in concrete structures. Furthermore, a method for coordinate transformation is presented to convert the obtained coordinates into executable ones for a robotic arm. Finally, the feasibility of this concrete defect repair method is validated through simulation and experiments.

Three-dimensional concrete printing (3DCP) technology begins to be adopted into construction application worldwide. Recent studies have focused on producing a higher concrete quality and offering a user-friendly construction process. Still, the 3DCP construction cost is unlikely to be lower than that of conventional construction, which is especially important for projects where the cost is sensitive. To broaden the 3DCP construction applications, reduction of the quantity of 3DCP material usage is needed. This work aims to perform structural analysis of several patterns of geometric textured 3DCP shell wall structures. 21 different cantilevered textured patterns of 3DCP shell wall structures were architecturally designed and then subjected to structural analysis by a finite element method (FEM). The results indicated that by designing appropriate patterns, the structural performance to weight ratio could be improved up to 300%. The study therefore offers an innovative design process for constructing 3DCP housing and suggests pre-construction analysis methods for 3DCP shell wall structures.

This work uses isogeometric analysis (IGA), which is based on nonlocal hypothesis and higher-order shear beam hypothesis, to investigate the static bending and free oscillation of a magneto-electro-elastic functionally graded (MEE-FG) nanobeam subject to elastic boundary constraints (BCs). The magneto-electric boundary condition and the Maxwell equation are used to calculate the variation of electric and magnetic potentials along the thickness direction of the nanobeam. This study is innovative since it does not use the conventional boundary conditions. Rather, an elastic system of straight and torsion springs with controllable stiffness is used to support nanobeams’ beginning and end positions, creating customizable BCs. The governing equations of motion of nanobeams are established by applying Hamilton’s principle and IGA is used to determine deflections and natural frequency values. Verification studies were performed to evaluate the convergence and accuracy of the proposed method. Aside from this, the impact of the input parameters on the static bending and free oscillation of the MEE-FG nanobeam is examined in detail. These findings could be valuable for analyzing and designing innovative structures constructed of functionally graded MEE materials.

Flexural performance of joints is critical for prefabricated structures. This study presents a novel channel steel-bolt (CB) joint for prefabricated subway stations. Full-scale tests are carried out to investigate the flexural behavior of the CB joint under the design loads of the test-case station. In addition, a three dimensional (3D) finite element (FE) model of the CB joint is established, incorporating viscous contact to simulate the bonding and detachment behaviors of the interface between channel steel and concrete. Based on the 3D FE model, the study examines the flexural bearing mechanism and influencing factors for the flexural performance of the CB joint. The results indicate that the flexural behavior of the CB joint exhibits significant nonlinear characteristics, which can be divided into four stages. To illustrate the piecewise linearity of the bending moment-rotational angle curve, a four-stage simplified model is proposed, which is easily applicable in engineering practice. The study reveals that axial force can enhance the flexural capacity of the CB joint, while the preload of the bolt has a negligible effect. The flexural capacity of the CB joint is approximate twice the value of the designed bending moment, demonstrating that the joint is suitable for the test-case station.

Civil infrastructure is prone to structural damage due to high geo-stress and other natural disasters, so monitoring is required. Data collected by structural health monitoring (SHM) systems are easily affected by many factors, such as temperature, sensor fluctuation, sensor failure, which can introduce a lot of noise, increasing the difficulty of structural anomaly identification. To address this problem, this paper designs a new process of structural anomaly identification under noisy conditions and offers Civil Infrastructure Denoising Autoencoder (CIDAE), a denoising autoencoder-based deep learning model for SHM of civil infrastructure. As a case study, the effectiveness of the proposed model is verified by experiments on deformation stress data of the Wuhan Yangtze River Tunnel based on finite element simulation. Investigation of the circumferential weld and longitudinal weld data of the case study is also conducted. It is concluded that CIDAE is superior to traditional methods.

In slurry shield tunneling, the stability of tunnel face is closely related to the filter cake. The cutting of the cutterhead has negative impact on the formation of filter cake. This study focuses on the formation time of dynamic filter cake considering the filtration effect and rotation of cutterhead. Filtration effect is the key factor for slurry infiltration. A multilayer slurry infiltration experiment system is designed to investigate the variation of filtrate rheological property in infiltration process. Slurry mass concentration C_L, soil permeability coefficient k, the particle diameter ratio between soil equivalent grain size and representative diameter of slurry particles d₁₀/D₈₅ are selected as independent design variables to fit the computational formula of filtration coefficient. Based on the relative relation between the mass of deposited particles in soil pores and infiltration time, a mathematical model for calculating the formation time of dynamic filter cake is proposed by combining the formation criteria and formation rate of external filter cake. The accuracy of the proposed model is verified through existing experiment data. Analysis results show that filtration coefficient is positively correlated with slurry mass concentration, while negatively correlated with the soil permeability coefficient and the particle diameter ratio between soil and slurry. As infiltration distance increases, the adsorption capacity of soil skeleton to slurry particles gradually decreases. The formation time of external filter cake is significantly lower than internal filter cake and the ratio is approximately 3.9. Under the dynamic cutting of the cutterhead, the formation time is positively associated with the rotation speed of cutter head, while negatively with the phase angle difference between adjacent cutter arm. The formation rate of external filter cake is greater than 98% when d₁₀/D₈₅≤ 6.1. Properly increasing the content or decreasing the diameter size of solid-phase particles in slurry can promote the formation of filter cake.

Using the complex variable method, an elastic analytical solution of the ground displacement caused by a shallow circular tunneling is derived. Non-symmetric deformation relative to the horizontal center line of the tunnel cross-section is used as a boundary condition. A comparison between the proposed analytical method and the Finite Element Method is carried out to validate the rationality of the obtained analytical solution. Two parameters in the Peck formula, namely the maximum settlement of the ground surface center and the width coefficient of settlement curve, are fitted and determined. We propose a modified Peck formula by considering three input parameters, namely the tunnel depth, tunnel radius, and the tunnel gap. The influence of these three parameters on the modified Peck formula is analyzed. The applicability of the modified Peck formula is further investigated by reference to six engineering projects. The ground surface displacement obtained by the explicit Peck formula is in good agreement with the field data, and the maximum error is only 1.3 cm. The proposed formula can quickly and reasonably predict the ground surface settlement caused by tunnelling.

This paper presents a calculation method that evaluates the extent of disturbance based on structural safety limits. Additionally, it summarizes the assessment methods for construction disturbance zones in shield tunneling near pile foundations, urban ground structures, and underground structures. Furthermore, taking the construction of the Chengdu Jinxiu Tunnel under bridges and urban pipelines as the engineering background, a study on the disturbance zoning of adjacent structures was conducted. The most intense disturbance occurs within one week of the tunnel underpass process, and it has a significant impact within a range of two times the tunnel diameter along the tunnel axis. The bridge pile and bridge deck experience less disturbance from tunnel approaching construction, with a maximum disturbance zone characterized as medium disturbance. On the other hand, underground pipelines are subjected to more significant disturbances from tunnel construction, with a maximum disturbance zone classified as strong disturbance. The implementation of “bridge pile sleeve valve pipe grouting & underground pipeline ground grouting & tunnel advance grouting” in the field effectively limits the vertical settlement of bridges and pipelines, resulting in a decrease of approximately 0.1 in disturbance level for the structures. The disturbance zoning method can assess tunnel disturbance with structures, identify high-risk interference locations, and facilitate targeted design reinforcement solutions.

The stick-slip action of strike-slip faults poses a significant threat to the safety and stability of underground structures. In this study, the north-east area of the Longmenshan fault, Sichuan, provides the geological background; the rheological characteristics of the crustal lithosphere and the nonlinear interactions between plates are described by Burger’s viscoelastic constitutive model and the friction constitutive model, respectively. A large-scale global numerical model for plate squeezing analysis is established, and the seemingly periodic stick-slip action of faults at different crust depths is simulated. For a second model at a smaller scale, a local finite element model (sub-model), the time history of displacement at a ground level location on the Longmenshan fault plane in a stick-slip action is considered as the displacement loading. The integration of these models, creating a multi-scale modeling method, is used to evaluate the crack propagation and mechanical response of a tunnel subjected to strike-slip faulting. The determinations of the recurrence interval of stick-slip action and the cracking characteristics of the tunnel are in substantial agreement with the previous field investigation and experimental results, validating the multi-scale modeling method. It can be concluded that, regardless of stratum stiffness, initial cracks first occur at the inverted arch of the tunnel in the footwall, on the squeezed side under strike-slip faulting. The smaller the stratum stiffness is, the smaller the included angle between the crack expansion and longitudinal direction of the tunnel, and the more extensive the crack expansion range. For the tunnel in a high stiffness stratum, both shear and bending failures occur on the lining under strike-slip faulting, while for that in the low stiffness stratum, only bending failure occurs on the lining.

Though a comprehensive in situ measurement project, the performance of a deep pit-in-pit excavation constructed by the top-down method in seasonal frozen soil area in Shenyang was extensively examined. The measured excavation responses included the displacement of capping beam and retaining pile, settlement of ground surface, and deformation of metro lines. Based on the analyses of field data, some major findings were obtained: 1) the deformations of retaining structures fluctuated along with the increase of temperature, 2) the deformation variation of retaining structures after the occurrence of thawing of seasonal frozen soil was greater than that in winter, although the excavation depth was smaller than before, 3) the influence area of ground settlement was much smaller because of the features of seasonal frozen sandy soil, 4) the displacement of metro line showed a significant spatial effect, and the tunnel lining had an obviously hogging displacement pattern, and 5) earth pressure redistribution occurred due to the combined effects of freezing-thawing of seasonal frozen soil and excavation, leading to the deformation of metro line. The influence area of ground settlement was obviously smaller than that of Shanghai soft clay or other cases reported in literatures because of special geological conditions of Shenyang. However, the deformation of metro lines was significantly lager after the thawing of the frozen soil, the stress in deep soil was redistributed, and the metro lines were forced to deform to meet a new state of equilibrium.

Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels. The development of computer vision has greatly promoted structural health monitoring. This study proposes a novel encoder–decoder structure, CrackRecNet, for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture. An image acquisition equipment is designed based on a camera, 3-dimensional printing (3DP) bracket and two laser rangefinders. A tunnel concrete structure crack (TCSC) image data set, containing images collected from a double-shield tunnel boring machines (TBM) tunnel in China, was established. Through data preprocessing operations, such as brightness adjustment, pixel resolution adjustment, flipping, splitting and annotation, 2880 image samples with pixel resolution of 448 × 448 were prepared. The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs. In the experiments, the proposed CrackRecNet showed better prediction performance than U-Net, TernausNet, and ResU-Net. This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.

Reinforced concrete (RC) flat slabs, a popular choice in construction due to their flexibility, are susceptible to sudden and brittle punching shear failure. Existing design methods often exhibit significant bias and variability. Accurate estimation of punching shear strength in RC flat slabs is crucial for effective concrete structure design and management. This study introduces a novel computation method, the jellyfish-least square support vector machine (JS-LSSVR) hybrid model, to predict punching shear strength. By combining machine learning (LSSVR) with jellyfish swarm (JS) intelligence, this hybrid model ensures precise and reliable predictions. The model’s development utilizes a real-world experimental data set. Comparison with seven established optimizers, including artificial bee colony (ABC), differential evolution (DE), genetic algorithm (GA), and others, as well as existing machine learning (ML)-based models and design codes, validates the superiority of the JS-LSSVR hybrid model. This innovative approach significantly enhances prediction accuracy, providing valuable support for civil engineers in estimating RC flat slab punching shear strength.

This study develops a machine-based washing and sieving method to accurately determine the soil particle size distribution for classification. This machine-based method is an extension of the recently developed and invented manual-based extended wet sieving method. It revises and upgrades a conventional rotary vibrating sieve machine with a steel sieve of aperture 0.063 mm and ten cloth sieves of apertures from 0.048 to 0.0008 mm for washing and sieving silt and clay. The machine generates three-dimensional motion and vibration, which allows particles smaller than the sieve aperture to pass through the sieve quickly. A common soil in Hong Kong, China, named completely decomposed tuff soil is used as test material for illustration. The silt and clay mixtures are successfully separated into many sub-groups of silt particles and clay particles from 0.063 to less than 0.0008 mm. The test results of the machine-based method are examined in detail and also compared with the manual-based method. The results demonstrate that the machine-based method can shorten the sieving duration and maintain high accuracy. The particle sizes of separated silt and clay particles are further examined with scanning electron microscopic images. The results further demonstrate that the machine-based method can accurately separate the particles of silt and clay with the pre-selected sieve sizes. This paper introduces a new machine-based washing and sieving method, and verifies the efficiency of the machine-based method, the accuracy of particle size, and its applicability to the classification of different types of soil.

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering structures. Most traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing time. To address this issue, we explore the potential of deep learning (DL) to increase the efficiency of crack detection and forecasting crack growth. However, there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks vary. In the paper, we present DL models for identifying cracks, especially on concrete surface images, and for predicting crack propagation. Firstly, SegNet and U-Net networks are used to identify concrete cracks. Stochastic gradient descent (SGD) and adaptive moment estimation (Adam) algorithms are applied to minimize loss function during iterations. Secondly, time series algorithms including gated recurrent unit (GRU) and long short-term memory (LSTM) are used to predict crack propagation. The experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding results. For evaluation of crack propagation, GRU and LSTM are used as DL models and results show good agreement with the experimental data.